Syntactico Semantic Word Representations in Multiple Languages

Our project is an extension of the project “Syntactico Semantic Word Representations in Multiple Languages”[1]. The previous project aims to improve the semantical representation of English vocabulary via incorporating the local context with global context and supplying homonymy and polysemy for multiple embeddings per word. It also introduces a new neural network architecture that learns the word embeddings from both local and global context and multiple embeddings of each word with homonymy and polysemy. Based on this neural network learning model, our project learns the embeddings for German words and improves the semantical representation of German vocabulary. After the learning procedure, we produce a new dataset of German word embeddings and visualize them in t-SNE figures.